© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47043
    Prev
    Next
    INDEX
    Explanations

    jQuery event delegation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     herunter
    -0.84
     Bre
    -0.78
     View
    -0.78
     array
    -0.77
     государственной
    -0.75
     Get
    -0.75
     نمک
    -0.73
     defendants
    -0.72
    gias
    -0.72
     SV
    -0.71
    POSITIVE LOGITS
    delegate
    1.26
     delegate
    1.02
     Nauka
    0.90
     Delegates
    0.88
     Delegate
    0.84
    clk
    0.83
    錀
    0.83
     Delegation
    0.82
     miele
    0.80
     Atalanta
    0.79
    Activations Density 0.022%

    No Known Activations